Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “factorization machine”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 703 records · Page 39
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Observational Constraints on Warm Cloud Microphysical Processes Using Machine Learning and Optimization Techniques

We introduce new parameterizations for autoconversion and accretion rates that greatly improve representation of the growth processes of warm rain. The new parameterizations capitalize on machine‐learning and optimization techniques and are constrained by in situ cloud probe measurements from the recent Atmospheric Radiation Measurement Program field campaign at Azores. The uncertainty in the new estimates of autoconversion and accretion rates is about 15% and 5%, respectively, outperforming existing parameterizations. Our results confirm that cloud and drizzle water content are the most important factors for determining accretion rates. However, for autoconversion, in addition to cloud water content and droplet number concentration, we discovered a key role of drizzle number concentration that is missing in current parameterizations. The robust relation between autoconversion rate and drizzle number concentration is surprising but real, and furthermore supported by theory. Thus, drizzle number concentration should be considered in parameterizations for improved representation of the autoconversion process.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2014

Development of negative ion extractor in the high-power and long-pulse negative ion source for fusion application

High power and long-pulse negative ion extractor, which is composed of the plasma grid (PG) and the extraction grid (EXG), is newly developed toward the neutral beam injector for heating and current drive of future fusion machines such as ITER, JT-60 Super Advanced and DEMO reactor. The PG is designed to enhance surface production of negative ions efficiently by applying the chamfered aperture. The efficiency of the negative ion production for the discharge power increased by a factor of 1.3 against that of the conventional PG. The EXG is also designed with the thermal analysis to upgrade the cooling capability for the long pulse operation of >1000 s required in ITER. Though the magnetic field for electron suppression is reduced to 0.75 of that in the conventional EXG due to this upgrade, it was experimentally confirmed that the extracted electron current can be suppressed to the allowable level for the long pulse operation. These results show that newly developed extractor has the high potential for the long pulse extraction of the negative ions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Redshifts of radio sources in the Million Quasars Catalogue from machine learning

ABSTRACT With the aim of using machine learning techniques to obtain photometric redshifts based upon a source’s radio spectrum alone, we have extracted the radio sources from the Million Quasars Catalogue. Of these, 44 119 have a spectroscopic redshift, required for model validation, and for which photometry could be obtained. Using the radio spectral properties as features, we fail to find a model which can reliably predict the redshifts, although there is the suggestion that the models improve with the size of the training sample. Using the near-infrared–optical–ultraviolet bands magnitudes, we obtain reliable predictions based on the 12 503 radio sources which have all of the required photometry. From the 80:20 training–validation split, this gives only 2501 validation sources, although training the sample upon our previous SDSS model gives comparable results for all 12 503 sources. This makes us confident that SkyMapper, which will survey southern sky in the u, v, g, r, i, z bands, can be used to predict the redshifts of radio sources detected with the Square Kilometre Array. By using machine learning to impute the magnitudes missing from much of the sample, we can predict the redshifts for 32 698 sources, an increase from 28 to 74 per cent of the sample, at the cost of increasing the outlier fraction by a factor of 1.4. While the ‘optical’ band data prove successful, at this stage we cannot rule out the possibility of a radio photometric redshift, given sufficient data which may be necessary to overcome the relatively featureless radio spectra.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Convection in Scaled Turbine Internal Cooling Passages With Additive Manufacturing Roughness

Abstract Additive manufacturing processes, such as direct metal laser sintering (DMLS), enable the creation of novel turbine cooling internal passages and systems. However, the DMLS method produces a significant and unique surface roughness. Previous work in scaled passages analyzed pressure losses and friction factors associated with the rough surfaces, as well as investigated the velocity profiles and turbulent flow characteristics within the passage. In this study, the heat transfer characteristics of scaled additively manufactured surfaces were measured using infrared (IR) thermography. Roughness panels were CNC machined from plates of aluminum 6061 to create near isothermal roughness elements when heated. Fluid resistance differences between the aluminum roughness panels and roughness panels constructed from ABS plastic using the same roughness patterns from McClain et al. (2020, “Flow in a Simulated Turbine Blade Cooling Channel With Spatially Varying Roughness Caused by Additive Manufacturing Orientation,” ASME Turbo Expo 2020, Turbomachinery Technical Conference and Exposition, Virtual Conference, Sept. 21–25, GT2020-16069) were investigated. Finally, the overall thermal performance enhancements and friction losses were assessed through the calculation of surface averaged “global thermal performance” ratios. The global thermal performance characterizations indicate results in-line with those found for traditional commercial roughness and slightly below traditional internal passage convection enhancement methods such as swirl chambers, dimples, and ribs. The passages investigated in this study do not include compressibility effects or the long-wavelength artifacts and channel geometric deviations observed by Wildgoose et al. (2020, “Impact of Additive Manufacturing on Internal Cooling Channels with Varying Diameters and Build Directions,” ASME Turbo Expo 2020, Turbomachinery Technical Conference and Exposition, Virtual Conference, Sept. 21–25, GT2020-15049). However, the results of this study indicate that, based on the roughness augmentation alone, artificial convective cooling enhancers such as turbulators or dimples may still be required for additively manufactured turbine component cooling.

Engineering↗
DOE OSTI2022

Matrix Multiply Performance of GPUs on Exascale-class HPE/Cray Systems

The computation of dense matrix-matrix products (GEMMs) is central to many modeling and simulation workloads as well as AI/ML deep learning campaigns. In fact, millions of dollars are spent annually on computing GEMMs, and large model training demands are increasing exponentially. Specialized processors such as GPUs are designed to perform well for these operations. However, the performance of GEMMs on GPUs can exhibit complex behaviors depending on many factors, making it challenging to optimize the performance of GEMMs on these processors. In this study we undertake an examination of GEMM performance on several leading GPU models taken from product lines of GPUs to be deployed in forthcoming exascale computing systems. We show results to illustrate the many factors that can affect performance of GEMMs on GPUs. We then present data collected from a large number of test runs for an example GEMM operation to show the dependence behaviors of GEMM rate on matrix dimensions. Finally, we show results from machine learning-based performance models using novel feature engineering methods to fit the measured performance, providing a potential basis for GEMM performance tuning and autotuning methods for GPUs. Recommendations are also given for how to achieve high GEMM performance on modern GPUs.

Melesse Vergara, Veronica↗
DOE OSTI2024

Uncertainty quantification in multivariable regression for material property prediction with Bayesian neural networks

With the increased use of data-driven approaches and machine learning-based methods in material science, the importance of reliable uncertainty quantification (UQ) of the predicted variables for informed decision-making cannot be overstated. UQ in material property prediction poses unique challenges, including multi-scale and multi-physics nature of materials, intricate interactions between numerous factors, limited availability of large curated datasets, etc. In this work, we introduce a physics-informed Bayesian Neural Networks (BNNs) approach for UQ, which integrates knowledge from governing laws in materials to guide the models toward physically consistent predictions. To evaluate the approach, we present case studies for predicting the creep rupture life of steel alloys. Experimental validation with three datasets of creep tests demonstrates that this method produces point predictions and uncertainty estimations that are competitive or exceed the performance of conventional UQ methods such as Gaussian Process Regression. Additionally, we evaluate the suitability of employing UQ in an active learning scenario and report competitive performance. The most promising framework for creep life prediction is BNNs based on Markov Chain Monte Carlo approximation of the posterior distribution of network parameters, as it provided more reliable results in comparison to BNNs based on variational inference approximation or related NNs with probabilistic outputs.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Causal machine learning uncovers conditions for convective intensification driven by organic and sulfate aerosols

Aerosols are often hypothesized to invigorate deep convective clouds (DCCs), but observational evidence remains limited and inconclusive. Clarifying this hypothesis is critical for regions vulnerable to thunderstorms and flooding, particularly highly polluted coastal cities. Leveraging a novel causal discovery–inference pipeline and high-resolution observations near Houston, TX, we identify multiple causal pathways among aerosols (mostly organic and sulfate), DCCs, and meteorological factors. However, a direct causal link from aerosols to DCCs is found to be uncommon, occurring in less than 35% of analyzed scenarios, and is characterized by strong conditionality and nonlinearity. When aerosol impacts on DCCs do occur, they can be substantial, enhancing DCC core heights by approximately 1.7 km, with 92% of this effect concentrated in warmer-phase cloud regions. Notably, the presence of sea breezes and the inclusion of all measured aerosol particles each enhance DCCs in over 95% of aerosol-sensitive cases.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Proxy quality control of biomass particles using thermogravimetric analysis and Gaussian process regression models

Abstract The temperature experienced by reactants during preparation in a reactor is a key component in determining the yield and homogeneity of usable chemical products such as biomass particles. Thermocouples with sensors can be used to monitor spatial temperature gradients within reactors but these sensors are often too expensive and/or invasive. The present work proposes a strategy to identify optimal machine learning models to infer the maximum effective temperature experienced by particles during oxidative biomass torrefaction using key thermochemical combustion parameters. The maximum rate of weight loss, the corresponding temperature, and fixed carbon content on a dry‐ash‐free basis are used as literature‐based predictor variables obtained from thermogravimetric analysis. The evaluation of 24 machine‐learning models using the standard tenfold cross‐validation method suggests that the exponential Gaussian process regression (GPR) model is the most effective, followed by other GPR models. These high‐performing GPR models were also utilized to predict the effective preparation temperature distribution of reactor‐produced biomass particles under eight conditions of varying residence time and air‐to‐biomass ratio. The effective preparation temperature and residence time of individual biomass particles were then encoded into the torrefaction severity factor and used to estimate the energy yield of the reactor output as a novel quality control method. © 2023 The Authors. Biofuels, Bioproducts and Biorefining published by Society of Industrial Chemistry and John Wiley & Sons Ltd.

09 BIOMASS FUELS↗
DOE OSTI2023

Time-Frequency Warped Waveforms for Well-Contained Massive Machine Type Communications

Herein this paper proposes a novel time-frequency warped waveform for short symbols, massive machine-type communication (mMTC), and internet of things (IoT) applications. The waveform is composed of asymmetric raised cosine (RC) pulses to increase the signal containment in time and frequency domains. The waveform has low power tails in the time domain, hence better performance in the presence of delay spread and time offsets. The time-axis warping unitary transform is applied to control the waveform occupancy in time-frequency space and to compensate for the usage of high roll-off factor pulses at the symbol edges. The paper explains a step-by-step analysis for determining the roll-off factors profile and the warping functions. Gains are presented over the conventional Zero-tail Discrete Fourier Transform-spread-Orthogonal Frequency Division Multiplexing (ZT-DFT-s-OFDM), and Cyclic prefix (CP) DFT-s-OFDM schemes in the simulations section.

42 ENGINEERING↗
DOE OSTI2023

Gray matter volume drives the brain age gap in schizophrenia: a SHAP study

Neuroimaging-based brain age is a biomarker that is generated by machine learning (ML) predictions. The brain age gap (BAG) is typically defined as the difference between the predicted brain age and chronological age. Studies have consistently reported a positive BAG in individuals with schizophrenia (SCZ). However, there is little understanding of which specific factors drive the ML-based brain age predictions, leading to limited biological interpretations of the BAG. We gathered data from three publicly available databases - COBRE, MCIC, and UCLA - and an additional dataset (TOPSY) of early-stage schizophrenia (82.5% untreated first-episode sample) and calculated brain age with pre-trained gradient-boosted trees. Then, we applied SHapley Additive Explanations (SHAP) to identify which brain features influence brain age predictions. We investigated the interaction between the SHAP score for each feature and group as a function of the BAG. These analyses identified total gray matter volume (group × SHAP interaction term β = 1.71 [0.53; 3.23]; p corr < 0.03) as the feature that influences the BAG observed in SCZ among the brain features that are most predictive of brain age. Other brain features also presented differences in SHAP values between SCZ and HC, but they were not significantly associated with the BAG. We compared the findings with a non-psychotic depression dataset (CAN-BIND), where the interaction was not significant. This study has important implications for the understanding of brain age prediction models and the BAG in SCZ and, potentially, in other psychiatric disorders.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Multi-fidelity modeling to predict the rheological properties of a suspension of fibers using neural networks and Gaussian processes

Unveiling the rheological properties of fiber suspensions is of paramount interest to many industrial applications. There are multiple factors, such as fiber aspect ratio and volume fraction, that play a significant role in altering the rheological behavior of suspensions. Three-dimensional (3D) numerical simulations of coupled differential equations of the suspension of fibers are computationally expensive and time-consuming. Machine learning algorithms can be trained on the available data and make predictions for the cases where no numerical data are available. However, some widely used machine learning surrogates, such as neural networks, require a relatively large training dataset to produce accurate predictions. Multi-fidelity models, which combine high-fidelity data from numerical simulations and less expensive lower fidelity data from resources such as simplified constitutive equations, can pave the way for more accurate predictions. Here, we focus on neural networks and the Gaussian processes with two levels of fidelity, i.e., high and low fidelity networks, to predict the steady-state rheological properties, and compare them to the single-fidelity network. High-fidelity data are obtained from direct numerical simulations based on an immersed boundary method to couple the fluid and solid motion. The low-fidelity data are produced by using constitutive equations. Multiple neural networks and the Gaussian process structures are used for the hyperparameter tuning purpose. Results indicate that with the best choice of hyperparameters, both the multi-fidelity Gaussian processes and neural networks are capable of making predictions with a high level of accuracy with neural networks demonstrating marginally better performance.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2019

Impact of High Q on ILC250 Upgrade for Record Luminosities and Path Toward ILC380

In this paper, we address the possibility of upgrading the ILC250 luminosity to $8.1 \times 10^{34}$, so that with the polarization feature, the effective luminosity will be $2.0 \times 10^{35}$ to compete with the FCC-ee luminosity and two detectors. The additional cost of the higher luminosity option will be about 2.2 B ILCU. The total cost for the ILC high luminosity machine will therefore be about 7.7 B versus FCC-ee 10.5 B. The AC power (267 MW) to operate the ILC luminosity upgrade will also be less than the AC power for FCC-ee (300 MW). Even with a modest quality factor Q of $1 \times 10^{10}$ for SRF cavities, the total cost of the upgrade will be 2.5 B ILCU additional over ILC250 baseline. We expect that, if approved, ILC250 will first be built at the baseline luminosity, operated for many years at this luminosity, and later upgraded to the high luminosity option. A significant part (RF power and cryo-power) of the additional cost for the luminosity upgrade overlaps with the expected additional costs for anticipated energy upgrade paths. A second ILC upgrade discussed in this paper will be to the higher energy Top Factory at 380 GeV. We also estimate the additional cost of this upgrade (1.5 B ILCU).

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Leveraging design of experiments to build chemometric models for the quantification of uranium (VI) and HNO3 by Raman spectroscopy

Partial least squares regression (PLSR) and support vector regression (SVR) models were optimized for the quantification of U(VI) (10–320 g L −1 ) and HNO 3 (0.6–6 M) by Raman spectroscopy with optimized calibration sets chosen by optimal design of experiments. The designed approach effectively minimized the number of samples in the calibration set for PLSR and SVR by selecting sample concentrations with a quadratic process model, despite complex confounding and covarying spectral features in the spectra. The top PLS2 model resulted in percent root mean square errors of prediction for U(VI), HNO 3 , and NO 3 − of 3.7%, 3.6%, and 2.9%, respectively. PLS1 models performed similarly despite modeling an analyte with a majority linear response (i.e., uranyl symmetric stretch) and another with more covarying vibrational modes (i.e., HNO 3 ). Partial least squares (PLS) model loadings and regression coefficients were evaluated to better understand the relationship between weaker Raman bands and covarying spectral features. Support vector machine models outperformed PLS1 models, resulting in percent root mean square error of prediction values for U(VI) and HNO 3 of 1.5% and 3.1%, respectively. The optimal nonlinear SVR model was trained using a similar number of samples (11) compared with the PLSR model, even though PLS is a linear modeling approach. The generic D-optimal design presented in this work provides a robust statistical framework for selecting training set samples in disparate two-factor systems. This approach reinforces Raman spectroscopy for the quantification of species relevant to the nuclear fuel cycle and provides a robust chemometric modeling approach to bolster online monitoring in challenging process environments.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Bridging the Gap Between Modern UX Design and Particle Accelerator Control Room Interfaces

Accelerator control systems often represent relatively complex and safety-sensitive human-machine interfaces within process control industries. These systems are technically robust and reflect the cumulative integration of solutions built and adapted across decades. One of the regular, unfortunate casualties of provisional accelerator control system updates is their human-system interfaces (HSIs) which often lag behind modern usability and design standards. An additional challenge is that although there is a multitude of established human factors (HF), and user experience (UX) principles for everyday digital applications, there are very few (if any) established principles for complex and safety-critical applications for an accelerator. This paper argues for the importance of established HF and UX principles (herein referred to as human-centered design principles) into the development of accelerator HSIs, emphasizing the need for clarity, consistency, responsiveness, and cognitive accessibility. Drawing from HF/UX best practices and human-centered design, this paper discusses how these approaches can enhance operator performance, reduce human error, and improve accelerator personnel collaboration. Case studies from Accelerator Control Operations Research Network (ACORN) at Fermilab are explored to demonstrate how interfaces built with human-centered design principles can scale with system complexity while remaining intuitive and efficient for diverse user roles including operators, machine experts, and engineers. By bridging the gap between traditional control system design and modern human-centered design methods, this paper provides a roadmap for evolving accelerator HSIs into more usable, maintainable, and effective tools.

Hill, Rachael [Idaho Natl. Lab.]↗
DOE OSTI2017

Multi-layered adaptative human-machine interface to support NPP operators - 104

The paper is aimed at improvement of situational awareness and reduction of information overload and during transients and abnormal operational modes. We investigate the possibility of implementation of a multi-layered interface concept for presentation of information to NPP operators. Four layers are suggested, namely: the structural layer representing process system in the form of a mimic diagram; the analytical layer intended to support cognitive activity performed by operator; the functional layer aimed at representation of the status of process functions performed by the plant equipment; and the reference layer containing any relevant information depending on the situation. All the layers can be superimposed on each other. Two factors influence on activation of layers, namely: category of operator and operational mode. The process of designing a multi-layered interface is based on functional analysis and illustrated in application to a simple heat generation system. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Machine Learning Based Prediction of Airflow Maldistribution in A-Type Heat Exchangers

Airflow maldistribution is one of the primary causes of performance degradation in air-to refrigerant heat exchangers (HX) and has been shown to decrease heat transfer by as much as 35%. As a result, many units are oversized to meet the target capacity, resulting in increased system cost and refrigerant charge. Several studies have explored how characteristics like package type and HX geometry impact the flow profile, but results are restricted to a limited range of parameters and cannot be extrapolated to new designs. In this work, a machine learning (ML) model is trained to predict the inlet flow profile of dry air entering A-type HXs across a broad range of geometries and conditions. Flow profiles are generated using a porous media CFD model and used to train an Artificial Neural Network (ANN) which exhibits maximum and average relative L2 norm errors of 0.48 and 0.05. Additionally, these predictions take less than a second to generate resulting in a speed up factor of 2.42E5 compared to CFD. Component-level simulations are conducted to determine the performance degradation resulting from the predicted airflow maldistribution profiles. The new ML model will enable rapid and accurate prediction of performance degradation resulting from airflow maldistribution in A-type HXs, allowing for more accurate and cost-effective HX design.

42 ENGINEERING↗
DOE OSTI2019

Soft Magnetic Multilayered FeSiCrB–Fe$_{x}$N Metallic Glass Composites Fabricated by Spark Plasma Sintering

Novel multilayered FeSiCrB–Fe $_{x}$ N ( x = 2–4) metallic glass composites were fabricated using spark plasma sintering of FeSiCrB amorphous ribbons (Metglas 2605SA3 alloy) and Fe $_{x}$ N ( x = 2–4) powder. Crystalline Fe $_{x}$ N can serve as a high magnetic moment, high electrical resistance binder, and lamination material in the consolidation of amorphous and nanocrystalline ribbons, mitigating eddy currents while boosting magnetic performance and stacking factor in both wound and stacked soft magnetic cores. Stacking factors of nearly 100% can be achieved in an amorphous ribbon/iron nitride composite. FeSiCrB–Fe $_{x}$ N multilayered metallic glass composites prepared by spark plasma sintering have the potential to serve as a next-generation soft magnetic material in power electronics and electrical machines.

36 MATERIALS SCIENCE↗
DOE OSTI2018

Combined function magnets in the RHIC electron storage ring

The maximum electron beam intensity, and therefore the luminosity, of the electron-ion collider eRHIC is limited by the available RF power, which has been chosen as 10 MW. To maximize the beam intensity in the presence of this limitation the bending radius needs to be chosen as large as possible. While this is generally accomplished by a FODO lattice in the arcs due to its high dipole packing factor, the quadrupoles in a separated-function lattice do not contribute to bending. The use of combined-function magnets instead of regular quadrupoles would allow the quadrupoles to contribute to the bending as well, which increases the actual bending radius of the machine. However, this measure also affects the damping distribution in the machine, and may even result in anti-damping, making the lattice not suitable as a storage ring. In the following we demonstrate how to convert a separated-function lattice to a combined-function lattice while simultaneously preserving the damping distribution.

43 PARTICLE ACCELERATORS↗